CN108664016B - Method and device for determining lane center line - Google Patents

Method and device for determining lane center line Download PDF

Info

Publication number
CN108664016B
CN108664016B CN201710209738.2A CN201710209738A CN108664016B CN 108664016 B CN108664016 B CN 108664016B CN 201710209738 A CN201710209738 A CN 201710209738A CN 108664016 B CN108664016 B CN 108664016B
Authority
CN
China
Prior art keywords
lane
point
target
line
road
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201710209738.2A
Other languages
Chinese (zh)
Other versions
CN108664016A (en
Inventor
陈偲
曾超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to CN201710209738.2A priority Critical patent/CN108664016B/en
Publication of CN108664016A publication Critical patent/CN108664016A/en
Application granted granted Critical
Publication of CN108664016B publication Critical patent/CN108664016B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
    • G06K9/00791Recognising scenes perceived from the perspective of a land vehicle, e.g. recognising lanes, obstacles or traffic signs on road scenes
    • G06K9/00798Recognition of lanes or road borders, e.g. of lane markings, or recognition of driver's driving pattern in relation to lanes perceived from the vehicle; Analysis of car trajectory relative to detected road
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/28Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
    • G01C21/30Map- or contour-matching
    • G01C21/32Structuring or formatting of map data
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38Electronic maps specially adapted for navigation; Updating thereof
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804Creation or updating of map data
    • G01C21/3807Creation or updating of map data characterised by the type of data
    • G01C21/3815Road data
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804Creation or updating of map data
    • G01C21/3807Creation or updating of map data characterised by the type of data
    • G01C21/3815Road data
    • G01C21/3819Road shape data, e.g. outline of a route
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02Control of position or course in two dimensions
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
    • G06K9/46Extraction of features or characteristics of the image
    • G06K9/4604Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes, intersections
    • G06K9/4638Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes, intersections by analysing connectivity relationships of elements of the pattern, e.g. by edge linking, by connected component or neighbouring slice analysis, by Markov Random Field [MRF] analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/60Analysis of geometric attributes
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/70Determining position or orientation of objects or cameras
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/09Arrangements for giving variable traffic instructions
    • G08G1/0962Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967Systems involving transmission of highway information, e.g. weather, speed limits
    • G08G1/096766Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission
    • G08G1/096775Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission where the origin of the information is a central station
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/09Arrangements for giving variable traffic instructions
    • G08G1/0962Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0968Systems involving transmission of navigation instructions to the vehicle
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/16Anti-collision systems
    • G08G1/167Driving aids for lane monitoring, lane changing, e.g. blind spot detection
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30248Vehicle exterior or interior
    • G06T2207/30252Vehicle exterior; Vicinity of vehicle
    • G06T2207/30256Lane; Road marking

Abstract

A method and apparatus for determining a lane centerline. The method comprises the following steps: acquiring a target lane in a road section with the changed lane number, wherein the target lane refers to an increased or decreased lane; for the first end of the target lane, determining the middle point of two end points of lane lines at two sides of the target lane at the first end as the central end point of the first end; for the second end of the target lane, determining the lane center point of the adjacent lane of the target lane as the center endpoint of the second end; and determining the lane central line of the target lane with the two central end points. For the lanes with the increased or decreased lane number in the road section with the changed lane number, the lane central line of the lane is determined by the scheme provided by the embodiment of the invention, so that the lane and the lane central lines of the lanes connected with the lane can be ensured to be continuous, and the accuracy of determining the lane central line is improved. In addition, the scheme provided by the embodiment of the invention completely adopts automatic calculation without manual intervention, and the efficiency of determining the center line of the lane is fully improved.

Description

Method and device for determining lane center line
Technical Field
The embodiment of the invention relates to the technical field of intelligent traffic, in particular to a method and a device for determining lane center lines.
Background
High-precision maps have been increasingly used in the fields of advanced driver assistance and unmanned driving. In high-precision maps, the lane center line with complete topological connections is important information required by the unmanned system. The lane central line does not really exist in the actual road and cannot be directly detected and obtained through the sensor.
In the related art, the geometric center line of the lane line on both sides of the lane is generally directly taken as the lane center line. The lane line refers to the left and right boundary lines of the lane. Referring collectively to FIG. 1, a schematic diagram of a roadway is shown. The driving direction of the road is from right to left. The lane lines of each lane are indicated by thick solid or dashed lines in the figure. For the road sections (such as the road section A and the road section C in the figure 1) with unchanged number of lanes, the geometric central lines of the lane lines on the two sides of the lane are used as lane central lines, the lane central lines are provided for the unmanned vehicle, and the unmanned vehicle runs along the lane central lines, so that the actual driving requirements can be met. For a road section (such as a road section B in fig. 1) with a changed number of lanes, if the geometric center lines of lane lines on both sides of the lane are provided to the unmanned vehicle as the lane center line, the unmanned vehicle travels along the lane center line, and the actual driving requirement cannot be met. Specifically, the number of lanes from 2 to 1 is reduced from 2 when the road segment a passes through the road segment B to reach the road segment C. The lanes 11 in the section B are decreasing lanes. The lane lines on both sides of the lane 11 are AB and AC, the geometric centerlines of AB and AC are AD, and D is the midpoint of the segment BC. If the AD is taken as the lane center line of the lane 11, the unmanned vehicle runs along the lane center line, and touches the curb at the point a, and the AD is not continuous with the lane center line of the road section C, so that the unmanned vehicle cannot smoothly run into the road section C.
Therefore, for the lanes increasing or decreasing in the road section where the number of lanes changes, the lane center line determined in the manner provided by the above-described related art is not accurate and cannot be provided as a guidance travel path to the unmanned vehicle. If the lane center line is determined by adopting a manual editing mode, time and labor are wasted.
Disclosure of Invention
In order to solve the problem that the lane center line determined by the method provided by the related art is not accurate for the lanes increased or decreased in the road section with the changed lane number, the embodiment of the invention provides a method and a device for determining the lane center line. The technical scheme is as follows:
in a first aspect, a method of determining a lane centerline is provided, the method comprising:
acquiring a target lane in a first road section, wherein the first road section is a road section with the number of lanes changing, the target lane is an increased or decreased lane, two end points of lane lines on two sides of the target lane at a first end of the target lane are respectively connected with the lane lines on two sides of the first lane, the lane lines on two sides of the target lane are intersected at an intersection point at a second end of the target lane, and the intersection point is connected with the lane line on one side of a second lane;
for the first end of the target lane, determining the middle point of two end points of the lane lines at the two sides of the target lane at the first end of the target lane as the central end point of the first end of the target lane;
for the second end of the target lane, determining a lane center point of an adjacent lane of the target lane as a center endpoint of the second end of the target lane, wherein the lane center point of the adjacent lane is a middle point of a mapping point of the intersection point and the intersection point, the mapping points of the intersection point and the intersection point are respectively located on two lane lines of the adjacent lane, and a connecting line of the intersection point and the mapping point of the intersection point is perpendicular to the driving direction of the adjacent lane;
and determining the lane central line of the target lane by taking the central endpoint of the first end of the target lane and the central endpoint of the second end of the target lane as two endpoints of the lane central line of the target lane.
In a second aspect, there is provided an apparatus for determining a lane centre line, the apparatus comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a target lane in a first lane, the first lane is a road section with the changed lane number, the target lane is an increased or decreased lane, two endpoints of lane lines on two sides of the target lane at a first end of the target lane are respectively connected with the lane lines on two sides of the first lane, the lane lines on two sides of the target lane are intersected at an intersection point at a second end of the target lane, and the intersection point is connected with the lane line on one side of a second lane;
the first determining module is used for determining the middle point of two end points of the lane lines at the two sides of the target lane at the first end of the target lane as the center end point of the first end of the target lane for the first end of the target lane;
a second determining module, configured to determine, for a second end of the target lane, a lane center point of an adjacent lane of the target lane as a center end point of the second end of the target lane, where the lane center point of the adjacent lane is a middle point of a mapping point of the intersection point and the intersection point, the intersection point and the mapping point of the intersection point are located on two lane lines on two sides of the adjacent lane, respectively, and a connection line of the intersection point and the mapping point of the intersection point is perpendicular to a driving direction of the adjacent lane;
and the third determining module is used for determining the lane central line of the target lane by taking the central endpoint of the first end of the target lane and the central endpoint of the second end of the target lane as two endpoints of the lane central line of the target lane.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
for the lanes with the increased or decreased lane number in the road section with the changed lane number, the lane central line of the lane is determined by the scheme provided by the embodiment of the invention, so that the lane and the lane central lines of the lanes connected with the lane can be ensured to be continuous, and the accuracy of determining the lane central line is improved. In addition, the scheme provided by the embodiment of the invention completely adopts automatic calculation without manual intervention, and the efficiency of determining the center line of the lane is fully improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic illustration of a related art provided for determining lane centerlines;
FIG. 2 is a flow chart of a method of determining a lane centerline provided by one embodiment of the present invention;
FIG. 3 shows a schematic view of a road;
FIG. 4 shows a schematic view of another road;
FIG. 5 shows a schematic diagram of the determination of lane centerlines in a manner that constructs Bezier curves;
FIG. 6 is a flow chart of a method of determining a lane centerline provided by another embodiment of the present invention;
FIG. 7 shows a schematic diagram of determining lane centerlines of non-target lanes;
FIG. 8 is a flow chart of a method of connecting lane centerlines at an intersection according to one embodiment of the present invention;
FIG. 9 shows a schematic diagram of a search area;
FIG. 10 is a schematic view of a direction corner and a position angle;
FIG. 11 is a schematic diagram illustrating the determination of a travel path by constructing a Bezier curve;
FIG. 12 is a block diagram of an apparatus for determining a lane centerline according to an embodiment of the present invention;
fig. 13 is a schematic structural diagram of a server according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
Before describing the embodiments of the present invention, some terms related to the embodiments of the present invention are first defined and explained.
Road: refers to the whole roadway between two adjacent intersections.
Lane: refers to the portion of the roadway on which a single tandem vehicle travels. A road includes one or more lanes.
Lane marking: which refers to the left and right boundaries on both sides of the lane.
Road section: refers to an entire road or a portion of a road. One road may be divided into a plurality of sections in a direction perpendicular to a traveling direction, and the sections are sequentially connected.
And (4) crossing: refers to one end of a road, and also refers to a place where roads meet. One intersection can communicate with a plurality of roads.
In the embodiment of the present invention, the execution subject of each step may be a server. For example, the server may be one server, a server cluster composed of a plurality of servers, or a cloud computing service center. Optionally, the server takes the lane line coordinate data of the high-precision map as input to determine lane center lines of the lanes; the server takes the lane central lines of all lanes and the lane driving direction attribute data as input to determine the connecting lines of the lane central lines at the intersection. Through the method, the server obtains the lane center line coordinate data with complete topological connection through automatic connection calculation, and provides a driving path with guiding significance for advanced assistant driving or unmanned driving.
Referring to fig. 2, a flowchart of a method for determining a lane center line according to an embodiment of the present invention is shown. The method may include several steps as follows.
In step 201, a target lane in a first road segment is acquired.
The first road section is a road section with a changed number of lanes. That is, the number of lanes of the adjacent road sections on both sides connected to the first road section is different. Assuming that the adjacent road sections on two sides connected with the first road section are a left adjacent road section and a right adjacent road section, and the driving direction is from left to right, namely the vehicle passes through the left adjacent road section, the first road section and the right adjacent road section in sequence, when the first road section is a road section with increased number of lanes, the number of lanes of the left adjacent road section is less than the number of lanes of the right adjacent road section; when the first road section is a road section with the reduced number of lanes, the number of lanes of the left adjacent road section is larger than that of lanes of the right adjacent road section. In one example, the left adjacent road segment of the first road segment includes 1 lane, the right adjacent road segment of the first road segment includes 2 lanes, and the number of lanes increases from 1 to 2 in the first road segment. In another example, the left adjacent road segment of the first road segment includes 3 lanes and the right adjacent road segment of the first road segment includes 2 lanes, and the number of lanes is reduced from 3 to 2 in the first road segment.
The target lane refers to an increasing or decreasing lane. Two endpoints of the lane lines on the two sides of the target lane at the first end of the target lane are respectively connected with the lane lines on the two sides of the first lane, the lane lines on the two sides of the target lane are intersected at an intersection point at the second end of the target lane, and the intersection point is connected with the lane line on one side of the second lane.
Taking the road shown in fig. 3 as an example, the driving direction of the road is from right to left, and the lane lines of the lanes are shown by thick solid lines or dashed lines in the figure. In fig. 3, a section B belongs to a first section (i.e., a section in which the number of lanes changes), and the section B includes a target lane 31 (i.e., a reduced lane in the section B). The lane lines on both sides of the target lane 31 are AB and AC. In fig. 3, the right end of the target lane 31 is a first end of the target lane 31, and the left end of the target lane 31 is a second end of the target lane 31. The two end points of the two side lane lines AB and AC of the target lane 31 at the first end of the target lane 31 are point B and point C, respectively, and the point B and the point C are connected to the two side lane lines BE and CF of the first lane 32, respectively. The both side lane lines AB and AC of the target lane 31 intersect at a point a at the second end of the target lane 31, and the point a is connected with a side lane line AG of the second lane 33.
In practical situations, there may be a lack of lane lines in the first segment. As shown in fig. 3, the lane line AB may be absent in the section B. And if the lane line is not lacked in the first road section, the server determines the target lane according to the lane line in the first road section. If the first road section lacks the lane line, the server supplements the lane line which is lacked in the first road section according to the lane lines of the adjacent road sections at two sides which are connected with the first road section; the target lane is then determined based on the lane line in the first road segment.
In one example, the missing lane lines in the first road segment are supplemented in the following manner: and for any first lane line end point, if the lane line connected with the first lane line end point is absent in the first road section, selecting a second lane line end point with the shortest distance to the first lane line end point, and connecting the first lane line end point and the selected second lane line end point to form a lane line. The first lane line end point is an end point of a lane line in a first adjacent road section close to the first road section, the second lane line end point is an end point of a lane line in a second adjacent road section close to the first road section, and the number of lanes in the first adjacent road section is larger than that of lanes in the second adjacent road section.
And step 202, for the first end of the target lane, determining the middle point of two end points of the lane lines on the two sides of the target lane at the first end of the target lane as the central end point of the first end of the target lane.
Referring to fig. 3 in combination, the midpoint between point B and point C is point D, which is the central endpoint of the first end of the target lane 31.
And step 203, for the second end of the target lane, determining the lane center point of the adjacent lane of the target lane as the center endpoint of the second end of the target lane.
The lane center points of the adjacent lanes are the intersection points (the intersection points of the lane lines on both sides of the target lane described above) and the middle points of the mapping points of the intersection points. The intersection points and the mapping points of the intersection points are respectively positioned on the lane lines at the two sides of the adjacent lane, and the connecting line of the intersection points and the mapping points of the intersection points is vertical to the driving direction of the adjacent lane.
The adjacent lane of the target lane and the target lane belong to the same first road section, and the adjacent lane of the target lane comprises: a lane to the left of and closest to the target lane, and/or a lane to the right of and closest to the target lane.
Referring collectively to fig. 3, the adjacent lane of the target lane 31 is shown at 34. The driving direction of the adjacent lane 34 is from right to left. The mapping point of the point a is a point a ', and the midpoint between the point a and the point a' is a point O, which is the central endpoint of the second end of the target lane 31.
The number of adjacent lanes of the target lane may be 1 or 2. When the number of the adjacent lanes of the target lane is only 1, the lane center point of the adjacent lane is the center endpoint of the second end of the target lane. When the number of the adjacent lanes of the target lane is 2, determining the central endpoint of the second end of the target lane by adopting the following method:
assuming that the adjacent lanes of the target lane include 2 adjacent lanes including the first adjacent lane and the second adjacent lane, the step 203 may include the following sub-steps:
step 203a, acquiring a lane central point of a first adjacent lane and a lane central point of a second adjacent lane;
step 203b, if the first distance is smaller than the second distance, determining the lane center point of the first adjacent lane as the center endpoint of the second end of the target lane;
step 203c, if the first distance is greater than the second distance, determining the lane center point of the second adjacent lane as the center endpoint of the second end of the target lane;
in step 203d, if the first distance is equal to the second distance, determining the lane center point of the first adjacent lane or the lane center point of the second adjacent lane as the center endpoint of the second end of the target lane.
The first distance is a distance between a center end point of the first end of the target lane and a lane center point of the first adjacent lane, and the second distance is a distance between the center end point of the first end of the target lane and a lane center point of the second adjacent lane.
Taking the road shown in fig. 4 as an example, the driving direction of the road is from left to right, and the lane lines of each lane are shown by thick solid lines or broken lines in the figure. In fig. 4, a section B belongs to a first section (i.e., a section in which the number of lanes changes), and the section B includes a target lane 41 (i.e., a reduced lane in the section B). The target lane 41 includes 2 adjacent lanes, such as adjacent lane 42 and adjacent lane 43 in fig. 4. The center point of the adjacent lane 42 is a point O1The center point of the adjacent lane 43 is a point O2If the central end point of the first end of the target lane 41 is the point D, the first distance is the point D and the point O1A second distance between points D and O2The distance between them.
Illustratively, the first distance and the second distance may be determined using several possible implementations as follows.
In a first possible implementation manner, a first distance is calculated directly according to coordinates of a center endpoint of a first end of a target lane and coordinates of a lane center point of a first adjacent lane; the second distance is calculated directly from the coordinates of the center point of the first end of the target lane and the coordinates of the lane center point of the second adjacent lane.
In a second possible implementation manner, a perpendicular point of a center endpoint of the first end of the target lane on a connecting line of a lane center point of the first adjacent lane and a lane center point of the second adjacent lane is obtained; respectively acquiring a distance (recorded as a third distance) between the vertical point and the lane center point of the first adjacent lane and a distance (recorded as a fourth distance) between the vertical point and the lane center point of the second adjacent lane; if the third distance is less than the fourth distance, determining that the first distance is less than the second distance; if the third distance is greater than the fourth distance, determining that the first distance is greater than the second distance;if the third distance is equal to the fourth distance, it is determined that the first distance is equal to the second distance. For example, with reference to FIG. 4 in combination, assume that point D is on line segment O1O2The upper vertical point is D'. If | D' O1|<|D′O2I, then I DO1|<|DO2L, |; if | D' O1|>|D′O2I, then I DO1|>|DO2L, |; if D' O1|=|D′O2I, then I DO1|=|DO2L. The above | | symbol represents the distance between two points.
In a third possible implementation manner, a sampling point is obtained on a lane central line of the first lane; acquiring an intersection point of an extension line of a connecting line of the sampling point and a center endpoint of a first end of the target lane on a connecting line of a lane center point of a first adjacent lane and a lane center point of a second adjacent lane; respectively acquiring a distance (recorded as a fifth distance) between the intersection point and the lane center point of the first adjacent lane and a distance (recorded as a sixth distance) between the intersection point and the lane center point of the second adjacent lane; if the fifth distance is less than the sixth distance, determining that the first distance is less than the second distance; if the fifth distance is greater than the sixth distance, determining that the first distance is greater than the second distance; if the fifth distance is equal to the sixth distance, it is determined that the first distance is equal to the second distance.
It should be noted that, in the embodiment of the present invention, the driving direction of the adjacent lane of the target lane refers to the entire driving direction of the entire lane to which the adjacent lane belongs. For example, the driving direction of the adjacent lane 34 of the target lane 31 in fig. 3 is from right to left, and the driving direction of the adjacent lanes 42 and 43 of the target lane 41 in fig. 4 is from left to right.
And step 204, determining the lane central line of the target lane by taking the central endpoint of the first end of the target lane and the central endpoint of the second end of the target lane as two endpoints of the lane central line of the target lane.
In one possible implementation, a straight line connecting a center endpoint of the first end of the target lane and a center endpoint of the second end of the target lane is taken as a lane center line of the target lane.
In another possible implementation, a curve connecting a center endpoint of the first end of the target lane and a center endpoint of the second end of the target lane is taken as a lane center line of the target lane.
In one example, a lane centerline of the target lane is determined in a manner that constructs a bezier curve. The step 204 includes the following substeps:
step 204a, determining a control point of the first Bezier curve;
the control points of the first Bezier curve include P0、P1、P2And P3,P0Is the central end point of the first end of the target lane, P3Is the central end point, P, of the second end of the target lane1Has the coordinates ofP2Has the coordinates ofWherein A is1And P0Coincidence of A3Is located on the lane central line A of the first lane1A2Above, A1、A3、B1、B3Respectively corresponding coordinates of each point. For example A3Is the lane central line A of the first lane1A2Upper distance A1Nearest sampling point, B1And P3Coincidence, B3Lane center line B in the second lane1B2Above, e.g. B3Is the lane center line B of the second lane1B2Upper distance B1Nearest sampling point, | A1B1I represents line segment A1B1Length of, | A1A3I represents line segment A1A3Length of, | B1B3I represents line segment B1B3Length of (k)1Is a preset constant. k is a radical of1Can be obtained from practical experience, and illustratively, k1Is in the range of 0.2 to 0.7.
Step 204b, determining sampling points on the first Bezier curve according to the control points of the first Bezier curve;
wherein, the coordinate C of the ith sampling point on the first Bezier curveiComprises the following steps:
Ci=P0t3+3P1t2(1-t)+3P2t(1-t)2+P3(1-t)3wherein P is1、P2、P3Respectively corresponding coordinates of each point.
Wherein the content of the first and second substances,n represents the number of sampling points on the first Bezier curve, n is an integer greater than 1, i is greater than or equal to 1 and less than or equal to n, and i is an integer.
And 204c, sequentially connecting the sampling points on the first Bezier curve to obtain a first Bezier curve, and taking the first Bezier curve as the lane center line of the target lane.
As shown in fig. 5, a schematic diagram of determining the lane center line of the target lane 51 in a manner of constructing a bezier curve is shown. The center point of the first end of the target lane 51 is P0The central end point of the second end of the target lane 51 is P3. The lane center line of the first lane 52 is A1A2,A1Is the end point of the first lane 52 on the lane center line that meets the first end of the target lane, A3Is a distance A1The closest sample point. The lane center line of the second lane 53 is B1B2,B1Is the end point of the second lane 53 on the lane center line that meets the second end of the target lane, B3Is a distance B1The closest sample point. The above description of the determination manner of the lane center lines of the first lane and the second lane and the related sampling points can be referred to the following related embodiments for determining the lane center line of the non-target lane. Get control point P0And A1Coincidence, control point P3And B1And the superposition can ensure that the center lines of the target lane and the connected lanes are continuous. Control point P1At A3A1On the extension line of (2), control point P2At B3B1On the extension line of (a). After determining the 4 control points of the first bezier curve, the coordinate of each sampling point on the first bezier curve is calculated by using the cubic formula of the bezier curve introduced in the above step 204b, and then the coordinates of each sampling point are connected to obtain the first bezier curve, which is shown as a curve P in fig. 50P3Shown. Curve P0P3I.e. the lane center line of the target lane 51.
The lane central line of the target lane is determined by constructing the Bezier curve, so that the curvature of the joint of the target lane and the lane central line of the adjacent road section of the target lane has continuity, the condition of sudden bending is avoided, the actual driving requirement is better met, and the lane central line can support advanced assistant driving and unmanned driving.
In addition, in the present embodiment, only the lane center line of the target lane is determined by constructing the bezier curve as an example, and in other embodiments, the lane center line of the target lane may also be determined by constructing a spline curve, which can also achieve the purpose of curvature continuity.
It should be noted that, in the embodiment of the present invention, the execution order of step 202 and step 203 is not limited, and step 202 may be executed before step 203, may be executed after step 203, or may be executed simultaneously with step 203.
In summary, for the lanes increased or decreased in the road section with the changed lane number, the lane center line of the lane is determined by the scheme provided by the embodiment of the invention, so that the lane and the lane center lines of the lanes connected with the lane are ensured to be continuous, and the accuracy of determining the lane center line is improved. In addition, the scheme provided by the embodiment of the invention completely adopts automatic calculation without manual intervention, and the efficiency of determining the center line of the lane is fully improved.
Next, a description will be given of a manner of determining the lane center line of the non-target lane. The non-target lane includes: the second road section is a road section of which the number of lanes is unchanged. For any one non-target lane, the server takes the center lines of the lane lines on two sides of the non-target lane as the lane center line of the non-target lane.
In one example, as shown in fig. 6, the lane center line of the non-target lane is determined using the following steps:
601, for any non-target lane, acquiring at least two groups of sampling points on lane lines on two sides of the non-target lane;
each group of sampling points comprises a first sampling point and a second sampling point, the first sampling point and the second sampling point are respectively positioned on one lane line of the non-target lane, and the connecting line of the first sampling point and the second sampling point is perpendicular to the driving direction of the non-target lane.
Step 602, acquiring a midpoint of a first sampling point and a midpoint of a second sampling point;
and 603, sequentially connecting the middle points of the groups of sampling points to obtain the lane center line of the non-target lane.
Assuming that the first sampling point is a sampling point Li on a lane line on the left side of the non-target lane, the second sampling point is a sampling point Ri on a lane line on the right side of the non-target lane, and a connection line of the first sampling point Li and the second sampling point Ri is perpendicular to the driving direction of the non-target lane, wherein i is a positive integer. The midpoint Ci between the first sampling point Li and the second sampling point Ri can be calculated by the following formula:
Ci(x)=(Li(x)+Ri(x))/2;
Ci(y)=(Li(y)+Ri(y))/2;
Ci(z)=(Li(z)+Ri(z))/2;
wherein Ci (x), Ci (y), and Ci (z) are the x-axis, y-axis, and z-axis coordinates, respectively, of the midpoint Ci, Li (x), Li (y), and Li (z) are the x-axis, y-axis, and z-axis coordinates, respectively, of the sample point Li, and Ri (x), Ri (y), and Ri (z) are the x-axis, y-axis, and z-axis coordinates, respectively, of the sample point Ri. The midpoint Ci, the first sample point Li, and the second sample point Ri are in the same coordinate system. The above formula can be equivalently expressed as: ci is (Li + Ri)/2.
And after the server acquires the middle points Ci of the first sampling point Li and the second sampling point Ri, sequentially connecting all the middle points Ci to obtain the lane center line of the non-target lane.
Referring collectively to fig. 7, a schematic diagram of determining lane centerlines of non-target lanes is shown. The driving direction of the non-target lane 70 is from left to right. The non-target lane 70 comprises a left lane line 71 and a right lane line 72, sampling points L1, L2, … and Ln exist on the left lane line 71, sampling points R1, R2, … and Rn exist on the right lane line 72, the server acquires the middle points C1, C2, … and Cn of each group of sampling points, and the middle points are sequentially connected to obtain a lane center line 73 of the non-target lane 70.
The lane center line of the non-target lane is determined through the method, the method is simple to implement, and the calculated amount is small.
Next, a method for connecting lane center lines at a road junction will be described with reference to the embodiment of fig. 8.
Step 801, select a combination of an exit lane and an entry lane with connectivity attributes at an intersection.
The connected attribute refers to an attribute that a vehicle enters an intersection from an exit lane and enters an entrance lane through the intersection. An exit lane is a lane through which a vehicle enters the intersection, and an entry lane is a lane into which a vehicle enters from the intersection. The server may determine whether the lane is an outgoing lane or an incoming lane based on the lane information stored in the high-precision map.
Optionally, step 801 comprises several sub-steps as follows:
step 801a, for each outgoing lane of the intersection, determining a search area corresponding to the outgoing lane according to the outgoing attribute of the outgoing lane.
Wherein the driving-out attribute comprises at least one of right turn, left turn, straight going and turning around. The server may acquire an exit attribute of the exit lane based on lane information (e.g., lane driving direction attribute data) stored in the high-precision map.
When the exit attributes of the exit lanes are different, the search areas corresponding to the exit lanes determined by the server are also different. Specifically, the following possibilities are included:
1. determining a first rectangular area G if the exit attribute of the exit lane comprises a right turn1H1I1J1For driving out of the search area corresponding to the lane, wherein G1Coinciding with a first endpoint, the first endpoint being an endpoint of a lane centerline of an exiting lane at an intersection, H1The central line of the lane located on the exiting lane is on the extension line of the intersection, I1J1And G1H1Parallel and at G1H1Right turn direction side of; as shown in part (a) of fig. 9;
2. determining a second rectangular area G if the exit attribute of the exit lane includes a left turn2H2I2J2For driving out of the search area corresponding to the lane, wherein G2Coinciding with the first end point, H2The central line of the lane located on the exiting lane is on the extension line of the intersection, I2J2And G2H2Parallel and at G2H2To the left-turn direction side; as shown in part (b) of fig. 9;
3. determining a third rectangular area G if the exit attribute of the exit lane includes straight traveling3H3I3J3For driving out the search area corresponding to the lane, wherein the first end point is G3H3Mid point of (A), I3J3And G3H3Parallel and at G3H3One side of the straight direction; as shown in part (c) of fig. 9;
4. determining a fourth rectangular area G if the exit attribute of the exit lane includes the U-turn4H4I4J4For driving out the search area corresponding to the lane, wherein the first end point is G4H4Mid point of (A), I4J4And G4H4Parallel and at G4H4To the left-turn direction side; as shown in part (d) of fig. 9.
The side length of each search area can be determined according to an actual experience value or intersection area. Optionally, each search area is a square area, and a length L of each search area may be obtained empirically, for example, the length L ranges from 10 meters to 100 meters.
Step 801b, searching and acquiring an entrance lane having a communication attribute with the exit lane in a search area corresponding to the exit lane.
The server searches and acquires one or more entering lanes with communication attributes with the exiting lanes in a searching area corresponding to the exiting lanes.
Optionally, step 801b includes the following two substeps:
step 801b1, calculating direction corner deviation and position included angle deviation corresponding to the driving lane for each driving lane in the search area corresponding to the driving lane;
the direction and rotation angle deviation refers to the absolute value of the difference between the direction and rotation angles in the ideal direction, and the position included angle deviation refers to the absolute value of the difference between the position included angle and the included angle in the ideal position.
Referring collectively to fig. 10, a schematic diagram of an intersection is shown. At the intersection, an outgoing lane 101 and an incoming lane 102 are included. D1Is a first end point, which is a lane center line D of the exiting lane 1011D2End points at the crossing, D3On the lane center line D of the exiting lane 1011D2The above. E1Is a second endpoint, which is the lane centerline E of the incoming lane 1021E2End points at the crossing, E3On the lane center line E of the incoming lane 1021E2The upper steering angle α meansAndthe included angle β meansAndthe included angle of (a).
Desired direction corner α0Angle β from ideal position0Is a preset value determined in advance based on the attributes of the drive-out, the desired direction angle α0Angle β from ideal position0Having directionality, in embodiments of the present invention, the clockwise direction is negative and the counter-clockwise direction is positive, with the angular units being degrees (°)0Angle of ideal position β0The correspondence between the drive-out attributes is shown in the following table-1:
egress attribute Desired direction corner α0 Desired included angle β0
Right turn -90° -45°
Left turn 90° 45°
Straight going
U-turn 180° 90°
TABLE-1
Step 801b2, if the direction corner deviation and the position included angle deviation corresponding to the entering lane meet the preset conditions, determining that the entering lane and the exiting lane have the communication property.
Optionally, a matching coefficient corresponding to the entering lane is obtained through calculation according to the direction corner deviation and the position corner deviation corresponding to the entering lane, and if the matching coefficient corresponding to the entering lane meets a preset condition, it is determined that the entering lane and the exiting lane have a communication attribute.
For example, the matching coefficient corresponding to the driving lane may be calculated by the following formula:
η=|α-α0|+|β-β0|-λ,
wherein η represents the matching coefficient corresponding to the driving lane, | α - α0I represents the deviation of the steering angle, which means the steering angle α is the ideal steering angle α0Absolute value of the difference, | β - β0I represents the deviation of the included angle of position, which means the included angle of position β and the ideal included angle of position β0λ is a preset threshold. The value of the preset threshold λ may be obtained empirically, for example, the value of the preset threshold λ ranges from 30 ° to 67.5 °.
Optionally, the preset condition is that the matching coefficient η is less than 0. For example, when the matching coefficient η corresponding to the entering lane is-5 °, it is determined that the entering lane and the exiting lane have a connected attribute.
Optionally, when the matching coefficients corresponding to the entering lanes are not less than 0, determining that the entering lane and the exiting lane with the smallest matching coefficients have a connected attribute. For example, the exit lane corresponds to a first entry lane and a second entry lane, wherein the matching coefficient corresponding to the first entry lane is 2 °, and the matching coefficient corresponding to the second entry lane is 5 °, it is determined that the first entry lane and the exit lane have a connectivity attribute.
Step 802, for each pair of combination of the outgoing lane and the incoming lane, determining a driving path connecting a first endpoint and a second endpoint according to a first endpoint of a lane center line of the outgoing lane at the intersection and a second endpoint of the lane center line of the incoming lane at the intersection.
In one possible implementation, a straight line connecting the first end point and the second end point is taken as the travel path.
In another possible implementation, a curve connecting the first end point and the second end point is used as the travel path.
In one example, a travel path connecting a first endpoint and a second endpoint is determined in a manner that constructs a bezier curve. The above step 802 includes the following sub-steps:
step 802a, determining a control point of a second Bezier curve;
the control points of the second Bezier curve include Q0、Q1、Q2And Q3,Q0And a first end point D1Coincidence, Q3And a second end point E1Coincidence, Q1Has the coordinates ofQ2Has the coordinates ofWherein D is3On the lane centre line D of the exiting lane1D2To above, D1、D3、E1、E3Respectively corresponding coordinates of each point. E.g. D3For driving out of lane center line D1D2Upper distance D1Nearest sampling point, E3On the lane centre line E of the driving-in lane1E2To e.g. E3For driving into the lane centre line E1E2Upper distance E1Nearest sampling point, | D1E1| represents a line segment D1E1Length, | D1D3| represents a line segment D1D3Length, | E1E3I denotes a line segment E1E3Length of (k)2Is a preset constant. k is a radical of2Can be obtained from practical experience, and illustratively, k2Is in the range of 0.2 to 0.7.
Step 802b, determining sampling points on the second Bezier curve according to the control points of the second Bezier curve;
wherein, the coordinate F of the j-th sampling point on the second Bezier curvejComprises the following steps:
Fj=Q0u3+3Q1u2(1-u)+3Q2u(1-u)2+Q3(1-u)3wherein Q is0、Q1、Q2、Q3Respectively corresponding coordinates of each point.
Wherein the content of the first and second substances,m represents the number of sampling points on the second Bezier curve, m is an integer greater than 1, j is greater than or equal to 1 and less than or equal to m, and j is an integer.
And step 802c, sequentially connecting the sampling points on the second Bezier curve to obtain a second Bezier curve, and using the second Bezier curve as a driving path connecting the first endpoint and the second endpoint.
As shown in fig. 11, a schematic diagram of the determination of the travel path in the manner of constructing a bezier curve is shown. The center line of the lane of the exiting lane 101 is D1D2The first end point is D1,D3Is a distance D1The closest sample point. The center line of the lane 102 is E1E2The second end point is E1,E3Is a distance E1The closest sample point. Get control point Q0And D1Coincidence, control point Q3And E1And the superposition can ensure that the driving path is continuous with the center line of the lane connected with the driving path. Control point Q1At D3D1On the extension line of (2), control point Q2At E3E1On the extension line of (a). After determining the 4 control points of the second bezier curve, the coordinate of each sampling point on the second bezier curve is calculated by using the cubic formula of the bezier curve introduced in the above step 802b, and then each sampling point is connected to obtain the second bezier curve, which is shown as a curve Q in fig. 110Q3Shown. Curve Q0Q3I.e. a travel path connecting the first end point and the second end point.
The driving path connecting the first end point and the second end point is determined by constructing the Bezier curve, so that the curvature of the connecting part of the driving path and the center line of the lane connected with the driving path has continuity, the situation of sudden bending is avoided, the actual driving requirement is better met, and the determined driving path is favorable for supporting high-grade assistant driving and unmanned driving.
In addition, in the present embodiment, the travel path connecting the first endpoint and the second endpoint is determined only by adopting a method of constructing a bezier curve as an example, and in other embodiments, the travel path may be determined by adopting a method of constructing a spline curve, and the purpose of curvature continuity can be achieved similarly.
In summary, the method provided in the embodiment of the present invention further determines the outgoing lane and the incoming lane according to the outgoing attribute after determining the lane center line of each lane, and then connects the lane center line of the outgoing lane and the lane center line of the incoming lane, so as to achieve the integrity of the connection of the lane center lines in the road topology.
The following are embodiments of the apparatus of the present invention that may be used to perform embodiments of the method of the present invention. For details which are not disclosed in the embodiments of the apparatus according to the invention, reference is made to the embodiments of the method and the system according to the invention.
Referring to fig. 12, a block diagram of an apparatus for determining a lane center line according to an embodiment of the present invention is shown. The apparatus has functions of implementing the above method examples, and the functions may be implemented by hardware or by hardware executing corresponding software. The apparatus may include: an obtaining module 1201, a first determining module 1202, a second determining module 1203, and a third determining module 1204.
An obtaining module 1201, configured to perform step 201.
A first determining module 1202, configured to perform the step 202.
A second determining module 1203, configured to execute the step 203.
A third determining module 1204, configured to perform step 204.
Optionally, the third determining module 1204 includes: a first determination unit, a second determination unit, and a third determination unit (not shown in the figure).
A first determining unit, configured to perform step 204 a.
A second determining unit, configured to perform step 204 b.
A third determining unit, configured to perform step 204c described above.
Optionally, the first determining module 1202 includes: a lane center point acquisition unit and a center end point determination unit (not shown in the figure).
A lane center point obtaining unit, configured to perform step 203 a.
A central endpoint determination unit for performing the above steps 203b, 203c and 203 d.
Optionally, the obtaining module 1201 includes: a lane acquisition unit and a lane line supplement unit (not shown in the figure).
And the lane acquiring unit is used for determining a target lane according to the lane line in the first road section if the lane line is not lacked in the first road section.
A lane line supplementing unit for supplementing a lane line lacking in the first road section according to lane lines of adjacent road sections on both sides connected to the first road section if the first road section lacks the lane line; and the lane acquisition unit is also used for determining a target lane according to the lane line in the first road section.
Optionally, the lane line supplementing unit is specifically configured to:
and for any first lane line end point, if the lane line connected with the first lane line end point is absent in the first road section, selecting a second lane line end point with the shortest distance to the first lane line end point, and connecting the first lane line end point and the selected second lane line end point to form a lane line. The first lane line end point is an end point of a lane line in a first adjacent road section close to the first road section, the second lane line end point is an end point of a lane line in a second adjacent road section close to the first road section, and the number of lanes in the first adjacent road section is larger than that of lanes in the second adjacent road section.
Optionally, the apparatus further comprises: a fourth determination module (not shown).
And the fourth determination module is used for taking the central lines of the lane lines on two sides of the non-target lane as the lane central lines of the non-target lane for any non-target lane. Wherein the non-target lane includes: the second road section is a road section of which the number of lanes is unchanged.
Optionally, the fourth determining module includes: a sampling point acquisition unit, a midpoint acquisition unit, and a midpoint connection unit (not shown in the figure).
A sampling point obtaining unit, configured to perform step 601.
A midpoint obtaining unit, configured to perform step 602.
A midpoint connecting unit, configured to perform step 603.
Optionally, the apparatus further comprises: a combination selection module and a path determination module (not shown in the figure).
A combination selection module, configured to perform step 801.
A path determining module, configured to perform step 802.
Optionally, a combination selection module comprising: an area determination unit and a lane search unit (not shown in the figure).
An area determination unit for performing the above step 801 a.
A lane searching unit for executing the above step 801 b.
Optionally, the area determining unit is specifically configured to:
determining a first rectangular area G if the exit attribute of the exit lane comprises a right turn1H1I1J1For driving out of the search area corresponding to the lane, wherein G1Coinciding with the first end point, H1The central line of the lane located on the exiting lane is on the extension line of the intersection, I1J1And G1H1Parallel and at G1H1Right turn direction side of; if it isDetermining a second rectangular area G if the exit attribute of the exit lane comprises a left turn2H2I2J2For driving out of the search area corresponding to the lane, wherein G2Coinciding with the first end point, H2The central line of the lane located on the exiting lane is on the extension line of the intersection, I2J2And G2H2Parallel and at G2H2To the left-turn direction side; determining a third rectangular area G if the exit attribute of the exit lane includes straight traveling3H3I3J3For driving out the search area corresponding to the lane, wherein the first end point is G3H3Mid point of (A), I3J3And G3H3Parallel and at G3H3One side of the straight direction; determining a fourth rectangular area G if the exit attribute of the exit lane includes a U-turn4H4I4J4For driving out the search area corresponding to the lane, wherein the first end point is G4H4Mid point of (A), I4J4And G4H4Parallel and at G4H4To the left turn direction side.
Optionally, a lane searching unit for performing the above steps 801b1 and 801b 2.
Optionally, the path determining module includes: a fourth determination unit, a fifth determination unit, and a sixth determination unit (not shown in the figure).
A fourth determining unit, configured to perform step 802a described above.
A fifth determining unit, configured to perform step 802 b.
A sixth determining unit, configured to perform step 802c above.
For specific details, reference may be made to the above-described method embodiments.
It should be noted that, when the apparatus provided in the foregoing embodiment implements the functions thereof, only the division of the functional modules is illustrated, and in practical applications, the functions may be distributed by different functional modules according to needs, that is, the internal structure of the apparatus may be divided into different functional modules to implement all or part of the functions described above. In addition, the apparatus and method embodiments provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments for details, which are not described herein again.
Referring to fig. 13, a schematic structural diagram of a server according to an embodiment of the present invention is shown. The server is used for implementing the method for determining the lane center line provided in the above embodiment. Specifically, the method comprises the following steps:
the server 1300 includes a Central Processing Unit (CPU)1301, a system memory 1304 including a Random Access Memory (RAM)1302 and a Read Only Memory (ROM)1303, and a system bus 1305 connecting the system memory 1304 and the central processing unit 1301. The server 1300 also includes a basic input/output system (I/O system) 1306, which facilitates transfer of information between devices within the computer, and a mass storage device 1307 for storing an operating system 1313, application programs 1314, and other program modules 1315.
The basic input/output system 13013 comprises a display 1308 for displaying information and an input device 1309, such as a mouse, keyboard, etc., for user input of information. Wherein the display 1308 and input device 1309 are connected to the central processing unit 1301 through an input-output controller 1310 connected to the system bus 1305. The basic input/output system 13013 may also include an input/output controller 1310 for receiving and processing input from a number of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, input-output controller 1310 also provides output to a display screen, a printer, or other type of output device.
The mass storage device 1307 is connected to the central processing unit 1301 through a mass storage controller (not shown) connected to the system bus 1305. The mass storage device 1307 and its associated computer-readable media provide non-volatile storage for the server 1300. That is, the mass storage device 1307 may include a computer-readable medium (not shown) such as a hard disk or CD-ROM drive.
Without loss of generality, the computer-readable media may comprise computer storage media and communication media. Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes RAM, ROM, EPROM, EEPROM, flash memory or other solid state memory technology, CD-ROM, DVD, or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that the computer storage media is not limited to the foregoing. The system memory 1304 and mass storage device 1307 described above may be collectively referred to as memory.
The server 1300 may also operate as a remote computer connected to a network via a network, such as the internet, according to various embodiments of the invention. That is, the server 1300 may be connected to the network 1312 through the network interface unit 1311, which is connected to the system bus 1305, or may be connected to other types of networks or remote computer systems (not shown) using the network interface unit 1311.
The memory also includes one or more programs stored in the memory and configured to be executed by one or more processors. The one or more programs include instructions for performing the server-side method.
In an exemplary embodiment, a non-transitory computer readable storage medium comprising instructions, such as a memory comprising instructions, executed by a processor of a server to perform the steps of the server side of the above method embodiments is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
Association relations, meaning that there may be three relations, e.g., A and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. As used herein, the terms "first," "second," and the like, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
The above description is only exemplary of the present invention and should not be taken as limiting the invention, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (21)

1. A method of determining a lane centerline, the method comprising:
acquiring a target lane in a first road section, wherein the first road section is a road section with the number of lanes changing, the target lane is an increased or decreased lane, two end points of lane lines on two sides of the target lane at a first end of the target lane are respectively connected with the lane lines on two sides of the first lane, the lane lines on two sides of the target lane are intersected at an intersection point at a second end of the target lane, and the intersection point is connected with the lane line on one side of a second lane;
for the first end of the target lane, determining the middle point of two end points of the lane lines at the two sides of the target lane at the first end of the target lane as the central end point of the first end of the target lane;
for the second end of the target lane, determining a lane center point of an adjacent lane of the target lane as a center endpoint of the second end of the target lane, wherein the lane center point of the adjacent lane is a middle point of a mapping point of the intersection point and the intersection point, the mapping points of the intersection point and the intersection point are respectively located on two lane lines of the adjacent lane, and a connecting line of the intersection point and the mapping point of the intersection point is perpendicular to the driving direction of the adjacent lane;
and determining the lane central line of the target lane by taking the central endpoint of the first end of the target lane and the central endpoint of the second end of the target lane as two endpoints of the lane central line of the target lane.
2. The method of claim 1, wherein determining the lane centerline of the target lane with the center endpoint of the first end of the target lane and the center endpoint of the second end of the target lane as two endpoints of the lane centerline of the target lane comprises:
determining a control point of the first Bezier curve;
determining sampling points on the first Bezier curve according to the control points of the first Bezier curve;
and sequentially connecting sampling points on the first Bezier curve to obtain the first Bezier curve, and taking the first Bezier curve as a lane center line of the target lane.
3. The method of claim 1, wherein the adjacent lanes of the target lane comprise 2 adjacent lanes of a first adjacent lane and a second adjacent lane;
the determining lane center points of adjacent lanes of the target lane as center end points of the second end of the target lane for the second end of the target lane comprises:
acquiring a lane central point of the first adjacent lane and a lane central point of the second adjacent lane;
if the first distance is smaller than the second distance, determining the lane center point of the first adjacent lane as the center endpoint of the second end of the target lane;
if the first distance is greater than the second distance, determining the lane center point of the second adjacent lane as the center endpoint of the second end of the target lane;
if the first distance is equal to the second distance, determining the lane center point of the first adjacent lane or the lane center point of the second adjacent lane as the center endpoint of the second end of the target lane;
the first distance is a distance between a center end point of the first end of the target lane and a lane center point of the first adjacent lane, and the second distance is a distance between the center end point of the first end of the target lane and the lane center point of the second adjacent lane.
4. The method of claim 1, wherein the obtaining the target lane in the first road segment comprises:
if the first road section does not lack the lane line, determining the target lane according to the lane line in the first road section;
if the first road section lacks the lane lines, supplementing the lane lines which are lacked in the first road section according to the lane lines of the adjacent road sections at two sides connected with the first road section; and determining the target lane according to the lane line in the first road section.
5. The method according to claim 4, wherein the supplementing of the lane lines missing in the first road section according to the lane lines of the two side-adjacent road sections connected to the first road section comprises:
for any first lane line end point, if a lane line connected with the first lane line end point is absent in the first road section, selecting a second lane line end point with the shortest distance to the first lane line end point, and connecting the first lane line end point and the selected second lane line end point to form a lane line;
the first lane line end point refers to an end point of a lane line in a first adjacent road section close to the first road section, the second lane line end point refers to an end point of a lane line in a second adjacent road section close to the first road section, and the number of lanes in the first adjacent road section is larger than that of lanes in the second adjacent road section.
6. The method of claim 1, further comprising:
for any non-target lane, taking the center lines of lane lines on two sides of the non-target lane as the lane center lines of the non-target lane;
wherein the non-target lane comprises: and any lane of the lanes except the target lane in the first road section and a second road section, wherein the second road section is a road section with unchanged lane number.
7. The method of claim 6, wherein for any one non-target lane, taking the center lines of the lane lines on both sides of the non-target lane as the lane center line of the non-target lane comprises:
for any non-target lane, at least two groups of sampling points are obtained on lane lines on two sides of the non-target lane, each group of sampling points comprises a first sampling point and a second sampling point, the first sampling point and the second sampling point are respectively located on one lane line of the non-target lane, and a connection line of the first sampling point and the second sampling point is perpendicular to the driving direction of the non-target lane;
acquiring the middle point of the first sampling point and the second sampling point;
and sequentially connecting the middle points of the groups of sampling points to obtain the lane center line of the non-target lane.
8. The method according to any one of claims 1 to 7, further comprising:
selecting a combination of an outgoing lane and an incoming lane with communication attributes at an intersection, wherein the communication attributes refer to attributes that vehicles enter the intersection from the outgoing lane and enter the incoming lane through the intersection;
and for each pair of combination of the outgoing lane and the incoming lane, determining a driving path connecting a first endpoint of the lane center line of the outgoing lane at the intersection and a second endpoint of the lane center line of the incoming lane at the intersection according to the first endpoint and the second endpoint.
9. The method of claim 8, wherein selecting a combination of an outgoing lane and an incoming lane having connectivity properties at an intersection comprises:
for each outgoing lane of the intersection, determining a search area corresponding to the outgoing lane according to the outgoing attribute of the outgoing lane, wherein the outgoing attribute comprises at least one of right turn, left turn, straight running and turning around;
and searching and acquiring an entering lane which has the communication attribute with the exiting lane in a searching area corresponding to the exiting lane.
10. The method of claim 9, wherein determining the search area corresponding to the outgoing lane based on the outgoing attribute of the outgoing lane comprises:
determining a first rectangular area G if the egress attribute of the egress lane includes the right turn1H1I1J1Search areas corresponding to the exit lanes, wherein G1Coincides with the first end point, H1The central line of the lane positioned on the exiting lane is positioned on the extension line of the intersection, I1J1And G1H1Parallel and at G1H1Right turn direction side of;
determining a second rectangular area G if the egress attribute of the egress lane includes the left turn2H2I2J2Search areas corresponding to the exit lanes, wherein G2Coincides with the first end point, H2The central line of the lane positioned on the exiting lane is positioned on the extension line of the intersection, I2J2And G2H2Parallel and at G2H2To the left-turn direction side;
determining a third rectangular area G if the exit attribute of the exit lane includes the straight run3H3I3J3A search area corresponding to the exit lane, wherein the first endpoint is G3H3Mid point of (A), I3J3And G3H3Parallel and at G3H3One side of the straight direction;
determining a fourth rectangular area G if the exit attribute of the exit lane includes the U-turn4H4I4J4A search area corresponding to the exit lane, wherein the first endpoint is G4H4Mid point of (A), I4J4And G4H4Parallel and at G4H4To the left turn direction side.
11. The method according to claim 9, wherein the searching for the incoming lane having the connectivity attribute with the outgoing lane in the search area corresponding to the outgoing lane comprises:
calculating a direction corner deviation and a position included angle deviation corresponding to the entering lane for each entering lane in the search area corresponding to the exiting lane, wherein the direction corner deviation is an absolute value of a difference value between a direction corner and an ideal direction corner, and the position included angle deviation is an absolute value of a difference value between a position included angle and an ideal position included angle;
and if the direction corner deviation and the position included angle deviation corresponding to the entering lane accord with preset conditions, determining that the entering lane and the exiting lane have the communication attribute.
12. The method of claim 8, wherein determining, for each pair of combination of an outgoing lane and an incoming lane, a travel path connecting a first endpoint of a lane centerline of the outgoing lane at the intersection and a second endpoint of the lane centerline of the incoming lane at the intersection, comprises:
determining a control point of a second Bezier curve;
determining sampling points on the second Bezier curve according to the control points of the second Bezier curve;
and sequentially connecting sampling points on the second Bezier curve to obtain the second Bezier curve, and using the second Bezier curve as a driving path connecting the first endpoint and the second endpoint.
13. An apparatus for determining a lane centerline, the apparatus comprising:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a target lane in a first lane, the first lane is a road section with the changed lane number, the target lane is an increased or decreased lane, two endpoints of lane lines on two sides of the target lane at a first end of the target lane are respectively connected with the lane lines on two sides of the first lane, the lane lines on two sides of the target lane are intersected at an intersection point at a second end of the target lane, and the intersection point is connected with the lane line on one side of a second lane;
the first determining module is used for determining the middle point of two end points of the lane lines at the two sides of the target lane at the first end of the target lane as the center end point of the first end of the target lane for the first end of the target lane;
a second determining module, configured to determine, for a second end of the target lane, a lane center point of an adjacent lane of the target lane as a center end point of the second end of the target lane, where the lane center point of the adjacent lane is a middle point of a mapping point of the intersection point and the intersection point, the intersection point and the mapping point of the intersection point are located on two lane lines on two sides of the adjacent lane, respectively, and a connection line of the intersection point and the mapping point of the intersection point is perpendicular to a driving direction of the adjacent lane;
and the third determining module is used for determining the lane central line of the target lane by taking the central endpoint of the first end of the target lane and the central endpoint of the second end of the target lane as two endpoints of the lane central line of the target lane.
14. The apparatus of claim 13, wherein the third determining module comprises:
a first determination unit configured to determine a control point of the first bezier curve;
the second determining unit is used for determining sampling points on the first Bezier curve according to the control points of the first Bezier curve;
and the third determining unit is used for sequentially connecting sampling points on the first Bezier curve to obtain the first Bezier curve, and taking the first Bezier curve as the lane center line of the target lane.
15. The apparatus of claim 13, wherein the adjacent lanes of the target lane comprise 2 adjacent lanes of a first adjacent lane and a second adjacent lane;
the first determining module includes:
a lane center point acquiring unit configured to acquire a lane center point of the first adjacent lane and a lane center point of the second adjacent lane;
the center endpoint determining unit is used for determining the lane center point of the first adjacent lane as the center endpoint of the second end of the target lane if the first distance is smaller than the second distance;
the center endpoint determining unit is further configured to determine a lane center point of the second adjacent lane as a center endpoint of the second end of the target lane if the first distance is greater than the second distance;
the center endpoint determining unit is further configured to determine a lane center point of the first adjacent lane or a lane center point of the second adjacent lane as a center endpoint of the second end of the target lane if the first distance is equal to the second distance;
the first distance is a distance between a center end point of the first end of the target lane and a lane center point of the first adjacent lane, and the second distance is a distance between the center end point of the first end of the target lane and the lane center point of the second adjacent lane.
16. The apparatus of claim 13, wherein the obtaining module comprises:
the lane acquiring unit is used for determining the target lane according to the lane line in the first road section if the first road section does not lack the lane line;
alternatively, the first and second electrodes may be,
a lane line supplementing unit configured to, if a lane line is absent in the first road segment, supplement the lane line absent in the first road segment according to lane lines of adjacent road segments on both sides connected to the first road segment; and the lane acquisition unit is used for determining the target lane according to the lane line in the first road section.
17. The apparatus of claim 16,
the lane line supplementing unit is used for selecting a second lane line end point with the shortest distance to the first lane line end point if a lane line connected with the first lane line end point is absent in the first road section for any first lane line end point, and connecting the first lane line end point and the selected second lane line end point to form a lane line;
the first lane line end point refers to an end point of a lane line in a first adjacent road section close to the first road section, the second lane line end point refers to an end point of a lane line in a second adjacent road section close to the first road section, and the number of lanes in the first adjacent road section is larger than that of lanes in the second adjacent road section.
18. The apparatus of claim 13, further comprising:
the fourth determination module is used for taking the central lines of lane lines on two sides of any non-target lane as the lane central lines of the non-target lane;
wherein the non-target lane comprises: and any lane of the lanes except the target lane in the first road section and a second road section, wherein the second road section is a road section with unchanged lane number.
19. The apparatus of any one of claims 13 to 18, further comprising:
the combination selection module is used for selecting a combination of an outgoing lane and an incoming lane with communication attributes at an intersection, wherein the communication attributes refer to attributes that vehicles enter the intersection from the outgoing lane and enter the incoming lane through the intersection;
and the path determining module is used for determining a driving path connecting a first endpoint and a second endpoint according to the first endpoint of the lane central line of the outgoing lane at the intersection and the second endpoint of the lane central line of the incoming lane at the intersection for each pair of combination of the outgoing lane and the incoming lane.
20. The apparatus of claim 19, wherein the combination selection module comprises:
the area determining unit is used for determining a search area corresponding to each outgoing lane of the intersection according to the outgoing attribute of the outgoing lane, wherein the outgoing attribute comprises at least one of right turn, left turn, straight running and turning around;
and the lane searching unit is used for searching and acquiring an entering lane which has the communication attribute with the exiting lane in a searching area corresponding to the exiting lane.
21. The apparatus of claim 19, wherein the path determination module comprises:
a fourth determination unit configured to determine a control point of the second bezier curve;
a fifth determining unit, configured to determine a sampling point on the second bezier curve according to the control point of the second bezier curve;
and the sixth determining unit is used for sequentially connecting sampling points on the second Bezier curve to obtain the second Bezier curve, and using the second Bezier curve as a driving path connecting the first endpoint and the second endpoint.
CN201710209738.2A 2017-03-31 2017-03-31 Method and device for determining lane center line Active CN108664016B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710209738.2A CN108664016B (en) 2017-03-31 2017-03-31 Method and device for determining lane center line

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN201710209738.2A CN108664016B (en) 2017-03-31 2017-03-31 Method and device for determining lane center line
US16/461,425 US20190347493A1 (en) 2017-03-31 2018-03-15 Method and apparatus for determining lane centerline
PCT/CN2018/079134 WO2018177131A1 (en) 2017-03-31 2018-03-15 Method and device for determining lane center line
EP18778088.7A EP3605264A4 (en) 2017-03-31 2018-03-15 Method and device for determining lane center line

Publications (2)

Publication Number Publication Date
CN108664016A CN108664016A (en) 2018-10-16
CN108664016B true CN108664016B (en) 2020-09-15

Family

ID=63674195

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710209738.2A Active CN108664016B (en) 2017-03-31 2017-03-31 Method and device for determining lane center line

Country Status (4)

Country Link
US (1) US20190347493A1 (en)
EP (1) EP3605264A4 (en)
CN (1) CN108664016B (en)
WO (1) WO2018177131A1 (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110132291A (en) * 2019-05-16 2019-08-16 深圳数翔科技有限公司 Grating map generation method, system, equipment and storage medium for harbour
CN110749329A (en) * 2019-10-26 2020-02-04 武汉中海庭数据技术有限公司 Lane level topology construction method and device based on structured road
CN112215882B (en) * 2020-12-10 2021-03-16 中智行科技有限公司 Center line processing method and device
CN112363413B (en) * 2020-12-31 2021-04-02 奥特酷智能科技(南京)有限公司 Method for generating automatic driving path of simulation vehicle

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101414407A (en) * 2007-10-16 2009-04-22 余亚莉 Intelligent dust type traffic sensor and signal control network and message transmission system thereof
CN102509067A (en) * 2011-09-22 2012-06-20 西北工业大学 Detection method for lane boundary and main vehicle position
CN102765385A (en) * 2011-05-05 2012-11-07 通用汽车环球科技运作有限责任公司 System and method for adjusting smoothness for lane centering steering control
CN105189255A (en) * 2013-05-09 2015-12-23 罗伯特·博世有限公司 Third order polynomial-based course prediction for driver assistance functions

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9341485B1 (en) * 2003-06-19 2016-05-17 Here Global B.V. Method and apparatus for representing road intersections
JP2010019759A (en) * 2008-07-11 2010-01-28 Mazda Motor Corp Traveling lane detector for vehicle
EP2455714B1 (en) * 2010-11-18 2019-01-23 Harman Becker Automotive Systems GmbH Method and device for displaying road segments
JP5810842B2 (en) * 2011-11-02 2015-11-11 アイシン・エィ・ダブリュ株式会社 lane guidance display system, method and program
US9396563B2 (en) * 2012-06-06 2016-07-19 Apple Inc. Constructing road geometry
CN202854837U (en) * 2012-09-26 2013-04-03 长安大学 Vehicle lane mark line detection device
CN103177246B (en) * 2013-03-26 2015-11-25 北京理工大学 Based on the dual model Lane detection method of dynami c block division
CN103903019B (en) * 2014-04-11 2017-12-15 北京工业大学 A kind of automatic generation method of multilane track of vehicle space-time diagram
CN103991449B (en) * 2014-06-12 2017-01-18 北京联合大学 Vehicle travelling control method and system
US9830517B2 (en) * 2014-06-19 2017-11-28 Toyota Motor Engineering & Manufacturing North America, Inc. Road branch detection and path selection for lane centering
US9227632B1 (en) * 2014-08-29 2016-01-05 GM Global Technology Operations LLC Method of path planning for evasive steering maneuver
CN104442814B (en) * 2014-10-31 2016-07-06 重庆长安汽车股份有限公司 Track based on deflection forecast algorithm keeps and automatic centering system and method
CN104700617B (en) * 2015-04-02 2016-03-16 武汉大学 Based on the high precision track information extracting method of low precision GPS track data
CN106441312A (en) * 2015-08-11 2017-02-22 高德软件有限公司 Guiding line generation method and guiding line generation device
CN106546260B (en) * 2015-09-22 2019-08-13 腾讯科技(深圳)有限公司 A kind of correcting method and system of traverse measurement data
CN105651295A (en) * 2016-01-15 2016-06-08 武汉光庭信息技术股份有限公司 Connection curve algorithm for constructing intersection entry and exit lane Links based on Bezier curve
CN105667518B (en) * 2016-02-25 2018-07-24 福州华鹰重工机械有限公司 The method and device of lane detection
CN105957342B (en) * 2016-05-30 2018-05-29 武汉大学 Track grade road plotting method and system based on crowdsourcing space-time big data

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101414407A (en) * 2007-10-16 2009-04-22 余亚莉 Intelligent dust type traffic sensor and signal control network and message transmission system thereof
CN102765385A (en) * 2011-05-05 2012-11-07 通用汽车环球科技运作有限责任公司 System and method for adjusting smoothness for lane centering steering control
CN102509067A (en) * 2011-09-22 2012-06-20 西北工业大学 Detection method for lane boundary and main vehicle position
CN105189255A (en) * 2013-05-09 2015-12-23 罗伯特·博世有限公司 Third order polynomial-based course prediction for driver assistance functions

Also Published As

Publication number Publication date
US20190347493A1 (en) 2019-11-14
WO2018177131A1 (en) 2018-10-04
CN108664016A (en) 2018-10-16
EP3605264A1 (en) 2020-02-05
EP3605264A4 (en) 2021-01-06

Similar Documents

Publication Publication Date Title
US10474162B2 (en) Autonomous vehicle localization using passive image data
CN107144285B (en) Pose information determination method and device and movable equipment
US10267634B2 (en) Distributed processing of pose graphs for generating high definition maps for navigating autonomous vehicles
US10197404B2 (en) Path curve confidence factors
US9068856B2 (en) Creating geometry for advanced driver assistance systems
Etienne et al. Spatio-temporal trajectory analysis of mobile objects following the same itinerary
KR102005203B1 (en) Driving planning device, driving support device, driving planning method
CN106840178B (en) A kind of map building based on ArcGIS and intelligent vehicle autonomous navigation method and system
US10147316B2 (en) Method, apparatus and computer program product for indexing traffic lanes for signal control and traffic flow management
CN102074047B (en) High-fineness urban three-dimensional modeling method
EP2443418B1 (en) Methods and systems for creating digital street network database
US7089162B2 (en) Navigation map creation system
CN104808688B (en) Unmanned aerial vehicle curvature continuous adjustable path planning method
CN107239076B (en) AGV laser SLAM method based on virtual scanning and distance measurement matching
US20150149080A1 (en) Generation of Intersection Information by a Mapping Service
JP2019120927A (en) Method and device for creating grid map
DE69729426T2 (en) Cartographic database device
US10859395B2 (en) Lane line creation for high definition maps for autonomous vehicles
WO2016146641A1 (en) Guided geometry extraction for localization of a device
CN101769754B (en) Quasi three-dimensional map-based mobile robot global path planning method
CN103336526B (en) Based on the robot path planning method of coevolution population rolling optimization
JP5591444B2 (en) Dual road shape representation for position and curvature-direction of travel
CN102176283B (en) Traffic network simplifying model and navigating method based on same
JP4875240B2 (en) Polygon road network data creation device, road map display device and method
US20130035853A1 (en) Prominence-Based Generation and Rendering of Map Features

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant